© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2456
    Prev
    Next
    INDEX
    Explanations

    specific metadata attributes related to events, including dates and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.03
    3:0.08
    4:0.36
    5:0.05
    6:0.02
    7:0.13
    8:0.02
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
    anwhile
    -3.24
    ��
    -2.95
    etically
    -2.80
     Bundy
    -2.80
    fortunately
    -2.75
    sterdam
    -2.75
    ovember
    -2.71
     roses
    -2.65
    zees
    -2.64
     negro
    -2.63
    POSITIVE LOGITS
     Description
    4.73
    Description
    4.53
     Status
    4.29
    Duration
    4.26
    Status
    4.20
     Position
    4.15
     Amount
    4.13
     Location
    4.09
     Duration
    4.07
    Subject
    4.06
    Activations Density 0.123%

    No Known Activations